superstring 0.0.1

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/.travis.yml

@@ -0,0 +1,8 @@
+rvm:
+  - 1.8.7
+  - 1.9.2
+  - 1.9.3
+  - 2.0.0
+  - ree
+
+script: "bundle exec rspec --color --format nested"

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in superstring.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2012 Harlan T Wood
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,88 @@
+SuperString   [![Build Status](https://travis-ci.org/harlantwood/superstring.png?branch=master)](https://travis-ci.org/harlantwood/superstring)
+===========
+
+Grant superpowers to instances of the Ruby String class.
+
+Split stings into sentences, convert to URL-friendly slugs, generate hashcodes, and more...
+
+Basic Usage
+-----------
+
+Install or bundle gem.  Then, simply:
+
+    require 'superstring'
+
+This will add new methods to the basic Ruby String class, which are described below.
+
+Slug generation
+---------------
+
+**Slugs safe for file names, and (arguably) URLs**
+
+    "Les Misérables".slug(:page)
+     => "Les-Misérables"
+
+`:page` is the default style, so this argument can be omitted:
+
+    "Les Misérables".slug
+     => "Les-Misérables"
+
+**Slugs safe for subdomains**
+
+    "Les Misérables".slug(:subdomain)
+    => "les-miserables"
+
+**Slugs safe for subdomains, padded with random digits to meet a given minimum length**
+
+    "Les Misérables".slug(:padded_subdomain, 20)
+     => "les-miserables-62858"
+
+Extract domain name from URI
+----------------------------
+
+    "http://www.mediawiki.org/wiki/Manual:$wgUrlProtocols".domain
+     => "mediawiki.org"
+
+Sentences
+---------
+
+    paragraph = "That that is, is. That that is not, is not. That is it, is it not?"
+    paragraph.sentences
+     => ["That that is, is.", "That that is not, is not.", "That is it, is it not?"]
+
+    poem = paragraph.sentence_poem
+     => "That that is, is.\nThat that is not, is not.\nThat is it, is it not?"
+    puts poem
+    That that is, is.
+    That that is not, is not.
+    That is it, is it not?
+
+SHA1 - SHA512 methods
+---------------------
+
+    "The quick brown fox jumps over the lazy dog".sha1
+     => "2fd4e1c67a2d28fced849ee1bb76e7391b93eb12"
+    "The quick brown fox jumps over the lazy dog".sha256
+     => "d7a8fbb307d7809469ca9abcb0082e4f8d5651e46d3cdb762d02d0bf37c9e592"
+    "The quick brown fox jumps over the lazy dog".sha384
+     => "ca737f1014a48f4c0b6dd43cb177b0afd9e5169367544c494011e3317dbf9a509cb1e5dc1e85a941bbee3d7f2afbc9b1"
+    "The quick brown fox jumps over the lazy dog".sha512
+     => "07e547d9586f6a73f73fbac0435ed76951218fb7d0c8d788a309d785436bbb642e93a252a954f23912547d1e8a3b5ed6e1bfd7097821233fa0538f3db854fee6"
+
+Whitespace
+----------
+
+    "  foo \r\n  bar  ".compact_whitespace
+     => "foo bar"
+    "  foo \r\n  bar  ".strip_lines!
+     => "foo\r\nbar"
+
+Check for inclusion in a given collection
+-----------------------------------------
+
+    collection = ["foo", "bar"]
+      => ["foo", "bar"]
+    "foo".in? collection
+      => true
+    "food".in? collection
+      => false

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/lib/superstring/ext/gollum.rb

@@ -0,0 +1,10 @@
+module Gollum
+  class Page
+    unless Page.respond_to?(:cname)
+      def self.cname(name, char_white_sub = '-', char_other_sub = '-')
+        name.respond_to?(:gsub) ? name.gsub(%r{\s}, char_white_sub).gsub(%r{[/<>+]}, char_other_sub) : ''
+      end
+    end
+  end
+end
+

data/lib/superstring/version.rb

@@ -0,0 +1,3 @@
+module Superstring
+  VERSION = "0.0.1"
+end

data/lib/superstring.rb

@@ -0,0 +1,171 @@
+# encoding: UTF-8
+
+require 'cgi'
+require 'digest/sha1'
+require 'active_support'
+require 'active_support/core_ext/string'
+require "superstring/version"
+require "superstring/ext/gollum"
+
+# Add functionality to basic String class:
+
+class ::String
+
+  include ActiveSupport::Inflector
+
+  MAXIMUM_SUBDOMAIN_LENGTH = 63  # This is a hard limit set by internet standards
+
+  def sha1
+    Digest::SHA1.hexdigest( self )
+  end
+
+  def sha256
+    Digest::SHA256.hexdigest( self )
+  end
+
+  def sha384
+    Digest::SHA384.hexdigest( self )
+  end
+
+  def sha512
+    Digest::SHA512.hexdigest( self )
+  end
+
+  def sentences
+    self.scan(
+      %r{
+        (?:
+          [^.!?\s]     # first char of sentence
+          [^\r\n]+?    # body of sentence
+          [.!?]+       # end of sentence
+          (?=\s|\z)    # followed by whitespace, or end of string
+        )
+      }x
+    )
+  end
+
+  def sentence_poem
+    sentences.join($/)
+  end
+
+  def slug(type = :page, minimum_subdomain_length = 8)
+    case type
+      when :page
+        page_name_safe
+      when :subdomain
+        padded_subdomain_safe(1)
+      when :padded_subdomain
+        padded_subdomain_safe(minimum_subdomain_length)
+      else
+        raise ArgumentError, "Unknown slug type #{type.inspect}"
+    end
+  end
+
+  def page_name_safe(char_white_sub = '-', char_other_sub = '-')
+    safer = self
+    if domain.present?
+      safer = CGI.unescape safer                    # convert %3D to '=', %20 to space, etc
+      safer = safer.gsub(/[?&=]/, char_other_sub)   # slug out standard query string chars
+    end
+    safer = Gollum::Page.cname(safer, char_white_sub, char_other_sub)
+    safer
+  end
+
+  def padded_subdomain_safe(minimum_subdomain_length)
+    if minimum_subdomain_length > MAXIMUM_SUBDOMAIN_LENGTH
+      raise ArgumentError.new("minimum_subdomain_length must not be greater than #{MAXIMUM_SUBDOMAIN_LENGTH} (was: #{minimum_subdomain_length}")
+    end
+
+    massaged = subdomain_safe
+    if massaged.size < minimum_subdomain_length
+      massaged << '-' unless massaged.empty?
+      massaged << ( minimum_subdomain_length - massaged.size ).times.map{ (rand*10).floor.to_s }.join
+    end
+    massaged
+  end
+
+  def subdomain_safe
+    safer = page_name_safe
+    safer = transliterate(safer)   # convert ø to o, å to a, etc
+    safer.downcase!
+    safer.gsub!(/[^a-z0-9\-]/, '-')
+    safer.gsub!(/^-+/, '')
+    safer = safer.slice(0, MAXIMUM_SUBDOMAIN_LENGTH)
+    safer
+  end
+
+  DOMAIN_SEGMENT_PATTERN = "[a-z0-9][a-z0-9-]+"
+  URI_PATTERN =
+    %r{
+      ^
+      \s*                                   # optional leading whitespace
+      (?:[a-z]+:)?                          # optional protocol, eg http:
+      //                                    # required //
+      (?:www\.)?                            # 'www.' is ignored
+      (
+        #{DOMAIN_SEGMENT_PATTERN}           # first domain segment
+        (?:\.#{DOMAIN_SEGMENT_PATTERN})+    # one or more additional domain segments
+      )
+      (?:/|$)                               # followed by a '/' or end of line
+    }ix
+
+  def domain
+    match(URI_PATTERN).to_a[1]
+  end
+
+  def strip_lines!
+    line_ending = match(/\r?\n/).to_a[0] || match(/\r/).to_a[0]
+    lines = line_ending ? split( line_ending ) : [ self ]
+    lines.map!{|line| line.strip }
+    processed = lines.join( line_ending )
+    processed.strip!
+    replace( processed )
+  end
+
+  def in?( collection )
+    collection.nil? ? false : collection.include?( self )
+  end
+
+  def compact_whitespace
+    gsub( /\s+/, ' ' ).strip
+  end
+
+  #LINE_ENDING = "\n"
+  #
+  #def break_long_lines!
+  #  lines = split( LINE_ENDING )
+  #  lines.map!( &:break_if_long )
+  #  processed = lines.join( LINE_ENDING )
+  #  replace( processed )
+  #end
+  #
+  #def break_if_long( max_length=100 )
+  #  lines = scan( chunk_pattern( max_length ) )
+  #  lines.map!( &:strip )
+  #  lines.join( LINE_ENDING )
+  #end
+  #
+  #def chunk_pattern( max_length )
+  #  %r{
+  #    (?:
+  #      (?:\b|^)
+  #      .{1,#{max_length}}        # lines shorter than max_length
+  #      (?:\s|$)
+  #      |
+  #      [^\s]{#{max_length+1},}   # lines longer than max_length, but with no whitespace, so they should not be broken
+  #    )
+  #  }x
+  #end
+  #
+  #ELLIPSES = '...'
+  #
+  #def truncate( max_length )
+  #  max_length -= ELLIPSES.size
+  #  result = match( chunk_pattern( max_length ) ) && $1
+  #  result ||= self[ 0...max_length ]
+  #  result.strip!
+  #  result << ELLIPSES if result.size < self.size
+  #  result
+  #end
+
+end

data/spec/superstring_spec.rb

@@ -0,0 +1,140 @@
+# encoding: UTF-8
+
+require File.expand_path('../lib/superstring', File.dirname(__FILE__))
+
+describe ::String do
+
+  describe "#sha1" do
+    it { "x".sha1.should =~ /^[0-9a-f]{40}$/ }
+  end
+
+  describe "#sha384" do
+    it { "x".sha384.should =~ /^[0-9a-f]{96}$/ }
+  end
+
+  describe "#sha512" do
+    it { "x".sha512.should =~ /^[0-9a-f]{128}$/ }
+  end
+
+  describe "#sentences" do
+    it {  "That that is, is.  That that is not, is not.\n\nThat is it...is it not?".sentences.should ==
+      ["That that is, is.", "That that is not, is not.", "That is it...is it not?"] }
+    it { "Foo. Bar fight! Baz? Yo!!!".sentences.should ==
+      ["Foo.", "Bar fight!", "Baz?", "Yo!!!"] }
+    it { "This file is called _Heart of the sun.wav Nov., 2012_.".sentences.should ==
+      ["This file is called _Heart of the sun.wav Nov., 2012_."] }
+  end
+
+  describe "#sentence_poem" do
+    it {  "That that is, is.  That that is not, is not.\n\nThat is it...is it not?".sentence_poem.should ==
+      "That that is, is.\nThat that is not, is not.\nThat is it...is it not?" }
+  end
+
+  describe "#strip_lines!" do
+    it { "  foo   bar  ".strip_lines!.should == "foo   bar" }
+    it { "  foo \n  bar  ".strip_lines!.should == "foo\nbar" }
+    it { "  foo \r  bar  ".strip_lines!.should == "foo\rbar" }
+    it { "  foo \r\n  bar  ".strip_lines!.should == "foo\r\nbar" }
+    it { "\n\nfoo\nbar\n\n".strip_lines!.should == "foo\nbar" }
+  end
+
+  describe "#compact_whitespace" do
+    it { "  foo   bar  ".compact_whitespace.should == "foo bar" }
+    it { "  foo \n  bar  ".compact_whitespace.should == "foo bar" }
+    it { "  foo \r  bar  ".compact_whitespace.should == "foo bar" }
+    it { "  foo \r\n  bar  ".compact_whitespace.should == "foo bar" }
+    it { "\n\nfoo\nbar\n\n".compact_whitespace.should == "foo bar" }
+  end
+
+  describe "#domain" do
+    it { "http://mediawiki.org".domain.should == "mediawiki.org"}
+    it { "http://mediawiki.org/".domain.should == "mediawiki.org"}
+    it { "http://mediawiki.org/foo.html".domain.should == "mediawiki.org"}
+    it { "https://mediawiki.org/".domain.should == "mediawiki.org"}
+    it { "gopher://mediawiki.org/".domain.should == "mediawiki.org"}
+    it { "anyprotocol://mediawiki.org/".domain.should == "mediawiki.org"}
+    it { "//mediawiki.org/".domain.should == "mediawiki.org"}
+    context "subdomains" do
+      it { "http://www.mediawiki.org/".domain.should == "mediawiki.org"}
+      it { "http://dance.dance.mediawiki.org/".domain.should == "dance.dance.mediawiki.org"}
+      it { "http://dance-dance-.mediawiki.org/".domain.should == "dance-dance-.mediawiki.org"}
+      it { "http://www.dance.dance.mediawiki.org/".domain.should == "dance.dance.mediawiki.org"}
+    end
+    context "invalid URIs" do
+      it { "".domain.should == nil }
+      it { "/mediawiki.org".domain.should == nil }
+      it { "http://mediawiki.org~~~".domain.should == nil }
+      it { "http://-illegal-subdomain.mediawiki.org".domain.should == nil }
+      it { "http://-illegal-subdomain.mediawiki.org".domain.should == nil }
+    end
+  end
+
+  describe "#slug" do
+    context "slugs safe for file names, and (arguably) URLs" do
+      it { "".slug(:page).should == "" }
+      it { "Welcome Visitors".slug(:page).should == "Welcome-Visitors" }
+      it { "  Welcome  Visitors  ".slug(:page).should == "--Welcome--Visitors--" }
+
+      it { "2012 Report".slug(:page).should == "2012-Report" }
+      it { "Ward's Wiki".slug(:page).should == "Ward's-Wiki" }
+      it { "holy cats !!! you don't say".slug(:page).should == "holy-cats-!!!-you-don't-say" }
+
+      it { "ø'malley".slug(:page).should == "ø'malley" }
+      it { "Les Misérables".slug(:page).should == "Les-Misérables" }
+
+      context "it should URL-decode characters in clear cases" do
+       it { "https://www.logilab.org/view?rql=WHERE%20X%20is%20IN%28MicroBlogEntry%2C%20BlogEntry%29%2C%20X%20title%20T".slug(:page).should ==
+          "https:--www.logilab.org-view-rql-WHERE-X-is-IN(MicroBlogEntry,-BlogEntry),-X-title-T" }
+      end
+
+      context "it should not URL-decode characters when the string is not a URL" do
+        it { "Pride? Yes, & that = prejudice. Sometimes %20 is just %20.".slug(:page).should ==
+          "Pride?-Yes,-&-that-=-prejudice.-Sometimes-%20-is-just-%20." }
+      end
+
+    end
+
+    context "slugs safe for subdomains" do
+      it { "".slug(:subdomain).should =~ /^\d$/ }
+
+      it { ("1234567890"*10).slug(:subdomain).should == "1234567890"*6 + "123" }  # 63 is the largest legal subdomain length
+
+      it { "Welcome Visitors".slug(:subdomain).should == "welcome-visitors" }
+      it { "  Welcome  Visitors  ".slug(:subdomain).should == "welcome--visitors--" }
+
+      it { "2012 Report".slug(:subdomain).should == "2012-report" }
+      it { "Ward's Wiki".slug(:subdomain).should == "ward-s-wiki" }
+      it { "holy cats !!! you don't say".slug(:subdomain).should == "holy-cats-----you-don-t-say" }
+
+      it { "ø'målley".slug(:subdomain).should == "o-malley" }
+      it { "Les Misérables".slug(:subdomain).should == "les-miserables" }
+
+      it { "https://www.logilab.org/view?rql=WHERE%20X%20is%20IN%28MicroBlogEntry".slug(:subdomain).should ==
+          "https---www-logilab-org-view-rql-where-x-is-in-microblogentry" }
+
+      it { "Pride? Yes, & that = prejudice. Sometimes %20 is just %20.".slug(:subdomain).should ==
+        "pride--yes----that---prejudice--sometimes--20-is-just--20-" }
+    end
+
+    context "padded to meet a given minimum length" do
+      it { "".slug(:padded_subdomain, 0).should == '' }
+      it { "".slug(:padded_subdomain, 10).should =~ /^\d{10}$/ }
+      it { "foo".slug(:padded_subdomain, 3).should =~ /^foo$/ }
+      it { "foo".slug(:padded_subdomain, 4).should =~ /^foo-$/ }
+      it { "foo".slug(:padded_subdomain, 5).should =~ /^foo-\d$/ }
+      it { "foo".slug(:padded_subdomain, 63).should =~ /^foo-\d{59}$/ }
+      it { lambda { "foo".slug(:padded_subdomain, 64) }.should raise_error(ArgumentError) }
+    end
+
+  end
+
+  describe "#in?" do
+    it { "foo".in?(["foo", "bar"]).should == true }
+    it { "f00".in?(["foo", "bar"]).should == false }
+    it { "foo".in?([]).should == false }
+    it { "foo".in?(nil).should == false }
+    it { "".in?([]).should == false }
+    it { "".in?(nil).should == false }
+  end
+
+end

data/superstring.gemspec

@@ -0,0 +1,24 @@
+# encoding: UTF-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'superstring/version'
+
+Gem::Specification.new do |gem|
+  gem.name          = "superstring"
+  gem.version       = Superstring::VERSION
+  gem.authors       = ["Harlan T Wood"]
+  gem.email         = ["code@harlantwood.net"]
+  gem.description   = %q{Grant superpowers to instances of the String class}
+  gem.summary       = %q{Split stings into sentences, convert to URL-friendly slugs, generate hashcodes, and more}
+  gem.homepage      = "https://github.com/harlantwood/superstring"
+
+  gem.files         = `git ls-files`.split($/)
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.require_paths = ["lib"]
+
+  gem.add_dependency 'activesupport', '>= 3.0.0'
+  gem.add_dependency 'i18n'
+
+  gem.add_development_dependency 'rspec'
+end

metadata

@@ -0,0 +1,106 @@
+--- !ruby/object:Gem::Specification
+name: superstring
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Harlan T Wood
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-12-18 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: activesupport
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 3.0.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 3.0.0
+- !ruby/object:Gem::Dependency
+  name: i18n
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Grant superpowers to instances of the String class
+email:
+- code@harlantwood.net
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .travis.yml
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/superstring.rb
+- lib/superstring/ext/gollum.rb
+- lib/superstring/version.rb
+- spec/superstring_spec.rb
+- superstring.gemspec
+homepage: https://github.com/harlantwood/superstring
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.24
+signing_key: 
+specification_version: 3
+summary: Split stings into sentences, convert to URL-friendly slugs, generate hashcodes,
+  and more
+test_files:
+- spec/superstring_spec.rb